Brain Networks and Medical Image Analysis

banner Jordi Casas cvc seminar

Abstract: In this seminar, the research conducted over the past years will be presented, along with new projects or ideas to be implemented in the future. The objective is to share prior experiences and promote synergies with other researchers and groups within the Computer Vision Center. Firstly, we will briefly discuss the research conducted during … Read more

Computational Models and Machine Learning for Neuroscience

banner Xim Cerda cvc seminar

Abstract: Curiosity, the intrinsic desire to know and explore, is a fundamental drive in human behavior with far-reaching implications. It serves as a catalyst for cognitive improvement, enriching internal models of the world and fostering non-instrumental information seeking. Recent studies highlight the neural underpinnings of curiosity, revealing activation of reward-related mesolimbic dopaminergic pathways, with the … Read more

Normalized Moments for Photo-realistic Style Transfer

banner trevor canham cvc seminar

Abstract: Due to the profundity of the concept of artistic style the optimal solution for style transfer is ill-defined. The variety of approaches that have been proposed represent partial solutions to varying degrees of efficiency, usability and quality of results. In this work a photo-realistic style transfer method for image and video based on vision … Read more

Calibration in Neural Networks: Understanding, Measuring & Improving it

banner adrian galdran cvc seminar

Abstract: A calibrated machine learning model produces probabilistic predictions that are well-aligned with real probabilities: it tends to be more certain when it is correct. Unfortunately, the unique characteristics of modern neural networks, e.g. over-parametrization or iterative training dynamics, can often result in overfitting the training data and generating over-confident predictions. The goal of this … Read more

Quantum Machine Learning

banner quantum machine learning cvc seminar

We are pleased to present the Quantum Machine Learning Group (QML-CVC) on Friday, October 20, 2023. We will introduce the people and the main lines of work of the QML-CVC Group, discussing fundamental components and scientific challenges of the Quantum Machine Learning field while identifying potential applications in Computer Vision. The event will start with … Read more

Intelligent Automation for AI-driven Document Understanding

Abstract: While machine learning models are continually improving, for most tasks they fail to achieve perfect predictive performance. In order to be a valuable tool in decision-making under uncertainty, it stands to reason that we want some statistical guarantees on the quality of probabilistic predictive models. Research into calibration regained popularity after repeated empirical observations … Read more

Multimedia content protection: from model-based to data-driven approaches

Abstract: In this talk, Dr Andrew D. Bagdanov, Dr Massimo Iuliani, Dr Dasara Shullani, Dr Daniele Baracchi & Simone Magistri will present the results of the research activity on multimedia content security carried out at the Information Engineering Department (DINFO) at the University of Florence. First, we will give a short introduction to the three … Read more

Interpretable-by-design Prototype-based Deep Learning

Abstract: Deep Learning justifiably attracted the attention and interest of the scientific community and industry as well as of the wider society and even policy makers. However, the predominant architectures (from Convolutional Neural Networks to Transformers) are hyper-parametric models with weights/parameters being detached from the physical meaning of the object of modelling. They are, essentially, … Read more

Meta-RL for Visual Semantic Navigation

Abstract: Semantic and goal-oriented visual navigation is one of the most prominent tasks performed by intelligent species in their daily lives. This task is defined as the ability we have to navigate through our environment, finding targets and enabling interaction with it. Navigation methods used in robotics can be divided into two main categories: geometry-based … Read more

Self-supervised Learning from Images, and Augmentations

Abstract:  In this talk, Yuki M. Asano will talk about pushing the limits of what can be learnt without using any human annotations. After a first overview of what self-supervised learning is, we will first dive into how clustering can be combined with representation learning using optimal transport ([1] @ ICLR’20), a paradigm still relevant … Read more